The cheapest, fastest lightweight inference @hannah_chuu @medha_rv
San Francisco, California
Joined March 2026
- Tweets5
- Following3
- Followers507
- Likes16
OneTriangle (YC S26) retweeted
very smart team that made several key technical leaps in KV Cache optimization to stand up a competitive inference service.
@OneTriangleAI (YC S26) is building the fastest lightweight, cheap inference and hosting @deepseek_ai V4 Flash today at $0.15/M input and $0.35/M output tokens. Live at onetriangle.ai/.
Our group of @MIT grads and olympiad medalists from @GoogleDeepMind, @JaneStreetGroup, and @NeurIPSConf /ICML publishers are setting a new standard for cost and latency efficiency using KV cache optimizations.
@OneTriangleAI (YC S26) is building the fastest lightweight, cheap inference and hosting @deepseek_ai V4 Flash today at $0.15/M input and $0.35/M output tokens. Live at onetriangle.ai/.
Our group of @MIT grads and olympiad medalists from @GoogleDeepMind, @JaneStreetGroup, and @NeurIPSConf /ICML publishers are setting a new standard for cost and latency efficiency using KV cache optimizations.
big things happening
We beat out @nvidia's KV cache transfer for KL divergence, and we're using it to build the fastest inference @TryTrustAI at @ycombinator.
17.8% less TTFT, $641 less per 1M requests, and 82.5% held-out top-1 agreement on Qwen 32B, prefilled from Qwen 8B.
OneTriangle (YC S26) retweeted
We beat out @nvidia's KV cache transfer for KL divergence, and we're using it to build the fastest inference @TryTrustAI at @ycombinator.
17.8% less TTFT, $641 less per 1M requests, and 82.5% held-out top-1 agreement on Qwen 32B, prefilled from Qwen 8B.
OneTriangle (YC S26) retweeted
We’re in YC!
Here’s what we’ve been up to:
> Dropped out of MIT
> Rejected our NYC quant and banking offers
> Moved to SF
> Fixed broken AI adoption with personalized one-click automations @TryTrustAI
Excited to put everything into our product, great start to a new chapter.
